EUVIMEDEUVIMED entdecken
Crossref

Dataset augmentation with multiple contrasts images in super-resolution processing of T1-weighted brain magnetic resonance images

Hajime Kageyama, Nobukiyo Yoshida, Keisuke Kondo, Hiroyuki Akai

Radiological Physics and Technology · 2025

DOI: 10.1007/s12194-024-00871-1 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Radiological Physics and Technology, 2025. Verfasst von Hajime Kageyama und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Institute of Medical Science, The University of Tokyo, 4-6-1 Shirokanedai, Minato-Ku, Tokyo, 108-8639, Japan. shadowpile@g.e…. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Brain, Image Processing, Computer-Assisted, Datasets as Topic. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 33 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study investigated the effectiveness of augmenting datasets for super-resolution processing of brain Magnetic Resonance Images (MRI) T1-weighted images (T1WIs) using deep learning. By incorporating images with different contrasts from the same subject, this study sought to improve network performance and assess its impact on image quality metrics, such as peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). This retrospective study included 240 patients who underwent brain MRI. Two types of datasets were created: the Pure-Dataset group comprising T1WIs and the Mixed-Dataset group comprising T1WIs, T2-weighted images, and fluid-attenuated inversion recovery images. A U-Net-based network and an Enhanced Deep Super-Resolution network (EDSR) were trained on these datasets. Objective image quality analysis was performed using PSNR and SSIM. Statistical analyses, including paired t test and Pearson's correlation coefficient, were conducted to evaluate the results. Augmenting datasets with images of different contrasts significantly improved training accuracy as the dataset size increased. PSNR values ranged 29.84-30.26 dB for U-Net trained on mixed datasets, and SSIM values ranged 0.9858-0.9868. Similarly, PSNR values ranged 32.34-32.64 dB for EDSR trained on mixed datasets, and SSIM values ranged 0.9941-0.9945. Significant differences in PSNR and SSIM were observed between models trained on pure and mixed datasets. Pearson's correlation coefficient indicated a strong positive correlation between dataset size and image quality metrics. Using diverse image data obtained from the same subject can improve the performance of deep-learning models in medical image super-resolution tasks.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingBrainImage Processing, Computer-AssistedDatasets as TopicHumansSignal-To-Noise RatioDeep LearningRetrospective StudiesMaleFemaleMiddle AgedAdult

Stichwörter der Autor:innen

Deep-learning methodsImage processingPeak signal-to-noise ratioStructural similaritySuper-resolution

Autor:innen und Institutionen

  • Department of Radiology, Institute of Medical Science, The University of Tokyo, 4-6-1 Shirokanedai, Minato-Ku, Tokyo, 108-8639, Japan. shadowpile@g.ecc.u-tokyo.ac.jp.
  • Graduate Division of Health Sciences, Komazawa University, 1-23-1 Komazawa, Setagaya-Ku, Tokyo, 154-8525, Japan. shadowpile@g.ecc.u-tokyo.ac.jp.
  • Department of Radiology, Institute of Medical Science, The University of Tokyo, 4-6-1 Shirokanedai, Minato-Ku, Tokyo, 108-8639, Japan.
  • Department of Radiological Technology, Faculty of Medical Technology, Niigata University of Health and Welfare, 1398 Shimami-Cho, Kita-Ku, Niigata, 950-3198, Japan.
  • Graduate Division of Health Sciences, Komazawa University, 1-23-1 Komazawa, Setagaya-Ku, Tokyo, 154-8525, Japan.

Zitieren

APA

Kageyama, H., Yoshida, N., Kondo, K., & Akai, H. (2025). Dataset augmentation with multiple contrasts images in super-resolution processing of T1-weighted brain magnetic resonance images. Radiological Physics and Technology. https://doi.org/10.1007/s12194-024-00871-1

Vancouver

Kageyama H, Yoshida N, Kondo K, Akai H. Dataset augmentation with multiple contrasts images in super-resolution processing of T1-weighted brain magnetic resonance images. Radiological Physics and Technology. 2025. doi:10.1007/s12194-024-00871-1

BibTeX
@article{Kageyama2025,
  author = {Kageyama, Hajime and Yoshida, Nobukiyo and Kondo, Keisuke and Akai, Hiroyuki},
  title = {Dataset augmentation with multiple contrasts images in super-resolution processing of T1-weighted brain magnetic resonance images},
  journal = {Radiological Physics and Technology},
  year = {2025},
  doi = {10.1007/s12194-024-00871-1}
}
Kostenlos starten →